This week; Yufei Ding, Yue Zhao, Xipeng Shen, Madanlal Musuvathi, and Todd Mytkowicz will be presenting Yinyang K-means at the 2015 International Conference on Machine Learning.
The algorithm guarantees the same results as traditional K-means, but it produces results with an order of magnitude higher performance.
An abstract of the paper and a PDF download can be accessed at Yinyang K-Means: A Drop-In Replacement of the Classic K-Means with Consistent Speedup.
A fun video to watch. Very Impressive!
The technique uses a genetic algorithm to training a neural network. A paper with more details can be found at, Evolving Neural Networks through Augmenting Topologies (NEAT)
Yoshua Bengio, Ian Goodfellow and Aaron Courville are writing a deep learning book for MIT Press. The book is not yet complete, but the drafts of the chapters are all available online. The authors are also collecting comments about the chapters before the book goes to press.
The book is broken into 3 sections:
- Math and Machine Learning Fundamentals
- Modern Deep Neural Networks
- Current Research in Deep Learning
The book is very technical and probably suitable for a graduate level course. However, if you have the time and interest, resources such as this are highly valuable.
If you are based near San Francisco and interested in machine learning, the Next.ML conference is going on this weekend, January 17, 2015. The conference is a bunch of workshops covering the latest trends in:
- DEEP LEARNING
- PROBABILISTIC PROGRAMMING
- PARALLEL LEARNING
- OTHER MACHINE LEARNING TOPICS AND TOOLS
The lineup of speakers is great, coming from places like MIT, Facebook, Stanford, Domino Data Labs, and others. Bring your laptop because all participants will leave the conference with lots of great software and datasets.
Note: If you would like to attend the conference, you can use the coupon code “media” to save 30% off the conference admission.
It was a 2-week intensive course focused on machine learning for big data. Some of the top academics in machine learning gave presentations. Most of the videos are fairly long (around 1 hour each), but a whole lot of material is covered.
All the CMU Machine Learning Summer School Videos are on Youtube.
Here is one lecture by Alex Smola on Scalable Machine Learning.
Onur Akpolat has put together A curated list of awesome big data frameworks and resources. The list is very extensive and includes: NoSQL databases, machine learning libraries, frameworks, filesystems and more.
On a similar note, Joseph Misiti has compiled a large list of machine learning specific resources. The list is titled, Awesome Machine Learning, and it includes resources for various languages, NLP, visualization, and more.
Both lists are on Github, so if you notice something missing from the list, feel free to add it. Contributions are welcome.
The excellent and popular Machine Learning class from Coursera and Andrew Ng starts today. This is the 3rd or 4th run of the course.
EdX, a MOOC site, is offering Learning From Data. This is a course about machine learning offered by Caltech. The course started yesterday, so there is still time to get started. The course has 2 tracks: audit and certificate. It looks great. Good Luck.
Hal Daumé III, Assistant Professor of Computer Science at the University of Maryland, has placed the contents of his book online. The book is titled A Course in Machine Learning.
Here is a small sampling of the chapters from A Course in Machine Learning:
- Decision Trees
- Linear Models
- Neural Networks
- Ensemble Methods
- Bayesian Learning